Reflections
Short signals, tied to real drops.
Principles in practice, written as the lab ships.
Field Notes are public signals. The full systems live inside the Vault.
Topic Clusters
Follow the linked note paths
These topical routes keep note discovery aligned with OpenClaw, Build AI Agent, and AI Agent Tools.
Coding-agent loops, terminal workflows, and guarded execution paths.
Blueprints, production patterns, and deploy paths for shipping agents.
MCP servers, registries, evals, and the tooling layer around agents.
A practical field guide to running coding agents safely: scope, isolation, verification, and review.
Datafast CLI is one of the practical ai agent tools in our stack: command-level analytics workflows, JSON artifacts, referrers, timeseries, and handoffs.
CLI-first SEO becomes one of the most practical ai developer tools when keywords, SERPs, audits, and ranks turn into machine-readable handoffs.
OpenClaw tutorial for Cosmo’s Mac mini setup: WhatsApp control, Tailscale recovery, tmux sessions, operator boundaries, and what breaks.
A deep, command-level teardown of claudeagentsdk (#005): an open-source agent workspace built around the Anthropic Agent SDK, with a FastAPI backend, a Vite/React frontend, and an optional Vercel Sandbox runner for async, reproducible runs.
A command-level teardown of the Starkslab inbox-to-execution loop: intake, triage, routing, artifact discipline, incidents, handoffs, metrics, and checklist controls.
A command-level, evidence-first teardown of where OpenClaw fits in an ai developer tools stack: architecture, workflows, incidents, throughput, and adoption boundaries.
A deep technical teardown of the Starkslab operating system: role boundaries, command-level workflows, incident logs, and the ai developer tools stack we use to ship continuously.
A practical, execution-first guide to build, run, debug, and harden your first AI agent with tools, guardrails, and production checks.
I built datafast-cli and pointed an autonomous AI agent at it. 13 commands, 2 bugs found, and the 5 principles that make CLI tools genuinely useful as AI agent tools.
I built MAF — a minimal AI agent framework in Python with one core loop, typed tool schemas, and JSONL traces. Here's how to build an AI agent from scratch, what broke against real APIs, and why minimal beats monolithic.
I built an X post scheduler from scratch — Express, Postgres, cron — and had an AI coding agent write most of it. Here's the architecture, the deployment, and why simple AI agent automation beats over-engineering.
I built trustmrr-cli — a TypeScript CLI giving AI agents access to verified revenue data for 4,900+ startups. Here's the architecture, the API workarounds, and why agent-native CLI tools are the missing layer.
Deep dive into OpenClaw's heartbeat and cron systems — the architecture that turns a reactive chatbot into an autonomous AI agent that wakes itself, schedules its own future, and improves while you sleep.
Deep dive into OpenClaw gateway-first architecture — how a single WebSocket, channel plugin system, and block streaming engine let one AI agent show up everywhere.
Deep dive into how OpenClaw agents modify their own personality files, create new skills, and drift into emergent behaviors — the architecture of AI self-modification.
I read OpenClaw's entire source code — gateway architecture, heartbeat system, session routing, queue modes, and the hidden coding agent SDK powering 1.2M AI agents.
Acceleration comes from shipping the smallest working system, then compounding it with tight feedback loops.